{
  "abstract": "MOTIVATION: Cold-start drug-target affinity prediction remains challenging because static interaction mechanisms cannot adapt to individual drug-target pairs. RESULTS: We propose PCIM-DTA, which constructs pair-level interaction representations and derives a pair-specific condition vector from global drug and target features. The condition vector modulates attention, pair-token features, distribution-aware recalibration, and regression parameters, while graph message passing captures higher-order dependencies. Experiments on Davis and BindingDB-Kd show that PCIM-DTA achieves competitive or superior performance under Warm, Cold-drug, Cold-target, Cold-both, and Scaffold-drug settings. Ablation studies support the contribution of each component. AVAILABILITY AND IMPLEMENTATION: The datasets used in this study are publicly available, including the Davis and BindingDB-Kd datasets. The implementation code of PCIM-DTA is publicly available at https://github.com/1322469934/PCIM-DTA.",
  "abstract_shown": true,
  "affiliations": [
    "Hunan Chuanshan Electronic Technology Co., Ltd , Hengyang, Hunan 421002,",
    "School of Computer Science and Engineering, Hunan Institute of Technology , Hengyang, Hunan 421002,"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Ziyou Zhou",
      "orcid": "0000-0002-0402-6537"
    },
    {
      "affs": [
        1
      ],
      "name": "Min Chen",
      "orcid": "0000-0002-0960-4447"
    },
    {
      "affs": [
        1
      ],
      "name": "周文剑"
    },
    {
      "affs": [
        1
      ],
      "name": "Qiong Xiao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/djb7fk511h4pg.bib",
  "cited_by": 8,
  "doi": "10.1093/bioinformatics/btag646",
  "fulltext_url": null,
  "id": "djb7fk511h4pg",
  "issns": [
    "1367-4803",
    "1367-4811"
  ],
  "landing_url": "https://doi.org/10.1093/bioinformatics/btag646",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "3002|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7204785900",
  "pdf_url": "https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btag646/70883127/btag646.pdf",
  "pmcid": "PMC13662694",
  "pmid": "42671309",
  "published": "2026-08-31",
  "publisher": "Oxford University Press",
  "ris": "https://research.draconitic.com/paper/djb7fk511h4pg.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T13:20:40Z",
      "native_id": "W7204785900",
      "source": "openalex",
      "url": "https://doi.org/10.1093/bioinformatics/btag646"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:3002|Computational Drug Discovery Methods",
      "subfield": "medicinal"
    }
  ],
  "title": "PCIM-DTA: pairwise conditional interaction modeling for drug–target affinity prediction under cold-start scenarios",
  "title_text": "PCIM-DTA: pairwise conditional interaction modeling for drug–target affinity prediction under cold-start scenarios",
  "type": "peer-reviewed",
  "updated_at": "2026-11-07T13:21:00Z",
  "url": "https://research.draconitic.com/paper/djb7fk511h4pg",
  "venue": "Bioinformatics",
  "versions": []
}